variant effect prediction

This paper introduces guided tokenization and domain adaptation to improve genomic language models' performance in classification and annotation tasks.

MultiGS is a genomic prediction platform that integrates various models for breeders, showing improved accuracy and efficiency in different prediction scenarios.

The paper compares machine learning models and summary statistics for inferring fixation times of hard sweeps and finds no significant improvement from machine learning.

The paper develops a computational pipeline to analyze TP53 missense mutations using quantum chemistry, integrating whole-exome sequencing data with chemoinformatics to study electronic properties of protein mutants.

The paper evaluates how well variant effect predictors perform across different genetic ancestries, finding comparable performance across major groups after accounting for allele frequency.

This study uses eHiCA to identify regulatory interactions at the PICALM-EED locus, showing distinct chromatin interactions for SNPs within a segregating haplotype.

The paper develops a Flex-Seq SNP panel for red raspberry and validates it through linkage maps and QTL identification for agronomic traits.

This study uses epigenetic annotations to prioritize SNPs in shrimp, improving genomic prediction accuracy and reducing costs.

This paper introduces SomaSV, a hybrid sequencing framework that improves somatic structural variant detection accuracy while reducing costs by combining long- and short-read data.

The paper develops a framework to predict mutation effects on transcription factor binding using mutational signatures in breast cancer genomes, revealing subtype-specific rewiring of gene regulatory networks.

The paper analyzes human spliceosome proteins to show that many contain over 40% disordered residues, driven by compositional bias and linked to post-translational modifications and cancer mutations.

The paper develops a machine learning model to predict bedaquiline resistance in Mycobacterium tuberculosis based on Rv0678 variants, achieving high accuracy in internal validation.

The paper classifies ABCC6 genetic variants using structural genomics to identify pathogenic mechanisms and reclassify variants of uncertain significance.

The paper introduces CLASTER, a deep learning model that predicts nascent transcription levels from chromatin landscape and 3D structure data, achieving high correlation with experimental measurements.

The paper presents a standardized RNA-seq analysis framework for rare disease diagnosis, identifying molecular diagnoses in 7.7% of previously undiagnosed cases.

This paper introduces quPCR, a calibrator-free method for absolute nucleic acid quantification by defining an intrinsic quantal unit based on replication system properties.

The paper develops a disease-specific histone modification prediction model using a large language model and MoE architecture, achieving high AUROC scores and identifying AD-associated variants.

This study identifies somatic mutations and mutational signatures associated with cancer-associated venous thromboembolism in a large cohort.

DERIVE predicts antigenic change across viruses using disentangled latent representations of evolutionary history, showing strong transferability to diverse viral families.

The paper develops a deep learning method to map SNV effects on translation efficiency, finding that variants influence disease risk through translation regulation.

OmiGA improves molQTL mapping in complex populations by using an efficient linear mixed model, enhancing power and reducing false positives.

MutPred-PPI predicts interaction-specific effects of missense variants using graph attention networks, showing strong performance on both seen and unseen proteins.

This study correlates 276 missense variants in PSEN1, PSEN2, and APP with Aβ peptide levels and variant effect predictors to assess pathogenicity in early-onset Alzheimer's disease.

This study develops a virus-mediated CRISPR/Cas9 system for genome editing in the parasitic plant P. japonicum, bypassing the need for tissue regeneration or floral dip transformation.

This study validates FF-enriched GW-NIPT for detecting 1 Mb CNVs with high performance across BMI groups and low failure rates.

The paper improves deep learning models for predicting sgRNA/Cas9 activity by optimizing data curation and filtering, resulting in better generalization across species and data types.

This paper introduces a Bayesian framework to quantify allele count evidence for variant pathogenicity using Bayes factors, showing compatibility with existing criteria while allowing tunable parameters.

This paper maps the functional effects of Parkin variants in mitophagy, distinguishing pathogenic from benign variants with high accuracy.

The paper functionally characterizes PRKN variants using a pooled assay, reclassifies variants of uncertain significance, and predicts Parkinson's disease age at onset.

The paper uses single-cell multi-omics data to identify asthma risk genes and their cell-type specific functions in lung immune cells.